| {"mean_reward": 634.5, "std_reward": 111.76873444751891, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-03T17:22:29.615275"} |
| {"mean_reward": 634.5, "std_reward": 111.76873444751891, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-03T17:22:29.615275"} |